Real-Time Hybrid Locomotion Mode Recognition for Lower Limb Wearable Robots

Abstract

Real-time recognition of locomotion-related activities is a fundamental skill that a controller of lower-limb wearable robots should possess. Subject-specific training and reliance on electromyographic interfaces are the main limitations of existing approaches. This study presents a novel methodology for realtime locomotion mode recognition of locomotion-related activities in lower-limb wearable robotics. A hybrid classifier can distinguish among seven locomotion-related activities. First, a timebased approach classifies between static and dynamical states based on gait kinematics data. Second, an event-based fuzzy logic method triggered by foot pressure sensors operates in a subjectindependent fashion on a minimal set of relevant biomechanical features to classify among dynamical modes. The locomotion mode recognition algorithm is implemented on the controller of a portable powered orthosis for hip assistance. An experimental protocol is designed to evaluate the controller performance in an out-of-lab scenario without the need for a subject-specific training. Experiments are conducted on six healthy volunteers performing locomotion-related activities at slow, normal, and fast speeds under the zero-torque and assistive mode of the orthosis. The overall accuracy rate of the controller is 99.4% over more than 10,000 steps, including seamless transitions between different modes. The experimental results show a successful subject-independent performance of the controller for wearable robots assisting locomotion-related activities.

A Real-Time Lift Detection Strategy for a Hip Exoskeleton

“…The optimal lift detection system for exoskeleton control should not only make accurate and timely detection of lift intentions, but also be simple and well integrated with exoskeleton devices, which is crucial for practical application. However, although there are some works using exoskeleton signals to detect other locomotion tasks (e.g., walking, stair ascent and descent, sitting down, and standing up) (Parri et al, 2017 ), to the best of our knowledge, there are no existing studies about the development of lift detection algorithms which use the signals from the exoskeleton's onboard sensors.…”

Human Body Mixed Motion Pattern Recognition Method Based on Multi-Source Feature Parameter Fusion

“…The recognition rate of only 6 types of sports modes including sitting, standing, walking, obstacle crossing, and going up and down using the sole force sensor is 98.8% [11]. Using 64 photoelectric matrix insoles and exoskeleton sensors to achieve 7 types of sports modes: ground-level walking, stair ascending, stair descending, sitting, standing, sit-to-stand and stand-to-sit, recognition rate 99.4% [12]. The combination of EMG and prosthetic mechanical sensors has achieved recognition rates of 97.7% and 97.8%, respectively, in the three scenarios of flat walking, stairs, and ramps [15,16].…”

“…After we improve the experimental system and algorithm in the future, the recognition rate will be improved. At the same time, compared with the use of photoelectric matrix pressure insole [12], we only select the most important three positions of the foot to arrange the pressure sensor, and the cheap scheme is more feasible in practical application. In fact, the foot segmentation in our system, which can adapt to different terrain, is an initial design for exoskeleton.…”

A Low-Back Exoskeleton can Reduce the Erector Spinae Muscles Activity During Freestyle Symmetrical Load Lifting Tasks

“…The APO is a robotic hip exoskeleton for the assistance of the hip flexion/extension movement, developed at The BioRobotics Institute of Scuola Superiore Sant'Anna. Previous versions of the device were presented in [17,18]. The mechanical structure of the APO included (i) a carbon-fiber frame structure connected to the user's trunk by means of an orthopedic shell and braces, and (ii) two rotating linkages connected at the user's thighs ( Figure 1A).…”